metadata

license: apache-2.0
base_model: google/electra-small-discriminator
tags:
  - generated_from_keras_callback
model-index:
  - name: nguyennghia0902/electra-small-discriminator_0.0001_32_15e
    results: []

nguyennghia0902/electra-small-discriminator_0.0001_32_15e

This model is a fine-tuned version of google/electra-small-discriminator on an unknown dataset. It achieves the following results on the evaluation set:

Train Loss: 0.5958
Train End Logits Accuracy: 0.8298
Train Start Logits Accuracy: 0.8077
Validation Loss: 0.2565
Validation End Logits Accuracy: 0.9243
Validation Start Logits Accuracy: 0.9233
Epoch: 14

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 0.0001, 'decay_steps': 23445, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
training_precision: float32

Training results

Train Loss	Train End Logits Accuracy	Train Start Logits Accuracy	Validation Loss	Validation End Logits Accuracy	Validation Start Logits Accuracy	Epoch
3.0253	0.3302	0.2968	2.2414	0.4704	0.4533	0
2.3162	0.4597	0.4260	1.8267	0.5511	0.5364	1
2.0285	0.5160	0.4813	1.5472	0.6109	0.5994	2
1.8125	0.5587	0.5287	1.2995	0.6688	0.6512	3
1.6192	0.5963	0.5677	1.0973	0.7105	0.7030	4
1.4482	0.6341	0.6066	0.8998	0.7637	0.7547	5
1.2931	0.6694	0.6423	0.7622	0.7920	0.7916	6
1.1518	0.6980	0.6741	0.6412	0.8260	0.8197	7
1.0351	0.7240	0.7025	0.5316	0.8518	0.8531	8
0.9269	0.7488	0.7270	0.4671	0.8701	0.8700	9
0.8354	0.7714	0.7489	0.3836	0.8910	0.8896	10
0.7520	0.7904	0.7699	0.3342	0.9048	0.9021	11
0.6869	0.8056	0.7848	0.2983	0.9134	0.9118	12
0.6320	0.8209	0.7994	0.2667	0.9223	0.9205	13
0.5958	0.8298	0.8077	0.2565	0.9243	0.9233	14

Framework versions

Transformers 4.39.3
TensorFlow 2.15.0
Datasets 2.18.0
Tokenizers 0.15.2